Objective To explore the diagnostic efficacy of machine learning in predicting perineural invasion(PNI)of invasive breast cancer based on MRI imaging features of breast cancer.Methods The data of 294 patients with invasive breast cancer confirmed by surgical pathology were retrospectively analyzed,and the patients were randomly divided into training set(205 cases,PNI 77 cases)and validation set(89 cases,PNI 33 cases)at a ratio of 7∶3.10 machine learning models were constructed by selecting training set clinical and radiographic features using single factor logistic regression.The area under the curve(AUC),accuracy(ACC),sensitivity(SE),specificity(SP),positive predictive value(PPV),and negative predictive value(NPV)were used to evaluate the predictive effi-cacy of different models for PNI,and the best model was determined.SHapley Additive exPlanation(SHAP)was used to visuaize the diagnosis process of the model.Results In the validation set,the multi-layer perceptron(MLP)model performed best,with AUC,ACC,SE,SP,PPV,and NPV of 0.91,0.89,0.79,0.95,0.90,and 0.88,respectively.Conclusion The model of MRI imaging fea-tures of breast cancer constructed by MLP machine learning model can effectively predict the preoperative PNI of invasive breast cancer.

Objective To explore the diagnostic efficacy of machine learning in predicting perineural invasion(PNI)of invasive breast cancer based on MRI imaging features of breast cancer.Methods The data of 294 patients with invasive breast cancer confirmed by surgical pathology were retrospectively analyzed,and the patients were randomly divided into training set(205 cases,PNI 77 cases)and validation set(89 cases,PNI 33 cases)at a ratio of 7∶3.10 machine learning models were constructed by selecting training set clinical and radiographic features using single factor logistic regression.The area under the curve(AUC),accuracy(ACC),sensitivity(SE),specificity(SP),positive predictive value(PPV),and negative predictive value(NPV)were used to evaluate the predictive effi-cacy of different models for PNI,and the best model was determined.SHapley Additive exPlanation(SHAP)was used to visuaize the diagnosis process of the model.Results In the validation set,the multi-layer perceptron(MLP)model performed best,with AUC,ACC,SE,SP,PPV,and NPV of 0.91,0.89,0.79,0.95,0.90,and 0.88,respectively.Conclusion The model of MRI imaging fea-tures of breast cancer constructed by MLP machine learning model can effectively predict the preoperative PNI of invasive breast cancer.

PURPOSE: Recent evidence suggests that B cells can both promote and inhibit the development and progression of allergic disease. However, the characteristics of B cell subsets in patients with allergic rhinitis (AR) have not been well documented. This study aimed to analyze the characteristics of B cell subsets in the peripheral blood of AR patients. METHODS: Forty-seven AR patients and 54 healthy controls were enrolled in this study, and the B cell subsets in peripheral blood of all subjects were analyzed by flow cytometry. Moreover, the serum total immunoglobulin E (IgE) and IgE concentrations secreted into the cultured peripheral blood mononuclear cells (PBMCs) were measured by using enzyme-linked immunosorbent assay. RESULTS: We found the peripheral blood of AR patients contained higher percentages of memory B cells, plasma cells, and CD19+CD24hiCD27+ regulatory B cells (Bregs) than those of age-matched healthy controls (P < 0.05), while the percentages of naïve B cells and CD19+CD24hiCD38hi Bregs were significantly lower in AR patients than in healthy individuals (P < 0.05). In addition, the serum total IgE and IgE concentrations secreted into the cultured PBMCs were elevated in AR patients than in the healthy controls (P < 0.05). CONCLUSIONS: Our findings indicate that AR patients were characterized by increase in terminally differentiated memory B cells or plasma cells and decreases in CD19+CD24hiCD38hi Breg cells in the peripheral blood.
B-Lymphocyte Subsets* ; B-Lymphocytes ; B-Lymphocytes, Regulatory ; Enzyme-Linked Immunosorbent Assay ; Flow Cytometry ; Humans ; Immunoglobulin E ; Immunoglobulins ; Memory ; Plasma Cells ; Rhinitis, Allergic*